Science at the Edge Friday April 13, 2018 1400 Biomedical Physical Science 11:30 am Yuafang Guan Department of Computational Medicine & Bioinformatics at the University of Michigan Title: Machine learning: from genomics to images Abstract: The research in my lab mainly focus on machine learning and its application in three core areas, which are image analysis, clinical informatics and functional genomics & proteomics. We are interested in applying deep learning to medical image analysis to aid disease diagnosis. Our algorithms identify micro-calcification in breast mammographic images and predicting heart disease subtypes with Electrocardiography (ECG) signals. Another branch of research is developing high-accuracy machine learning algorithms that predict diseases progression and clinical outcomes by leveraging genetic and clinical information. Related projects include kidney disease outcome prediction, survival time prediction (GuanRank), Alzheimer's disease prediction, Parkinson's disease prediction, anti-cancer drug synergy prediction, tumor heterogeneity prediction. The third branch aims to benefit the functional genomics and proteomics research filed. Past and on-going projects include the isoform-level analysis of single-cell sequencing data, the prediction of protein expression levels and developing a novel genome alignment tool (Seekmer). We are in active collaboration with nationwide projects including the NEPTUNE project and the MIDAS group in UM. Lerena R. Heintzelman Department of Physics & Astronomy Michigan State University 567 Wilson Rd. Room 3261 East Lansing, MI 48824 517-884-5513